跳到主要内容
知仓学习社ZHICANG

ad-library-teardown

Use when the user wants to analyze active ads from Meta/Facebook, Google, or LinkedIn ad libraries; tear down a competitor's messaging; extract hook…

不碰外部(只输出文字)无严重或高危命中ScrapeCreators/social-media-research-skills

它会碰到什么

扫了多少1 个文本文件,4 KB
它会碰到什么不碰外部(只输出文字)
命中总数0 处
命中统计严重 0 · 高 0 · 中 0 · 低 0

这一栏是扫描器报的事实,不是结论。命中多不等于有毒(安全工具、规则库、示例脚本本来就会包含危险写法),命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系,需要你自己看。

技能内容

Ad Library Teardown

Overview

Analyze public ads to understand a competitor's messaging, offers, creative strategy, and testing angles. The output should be a practical teardown marketers can use to write better ads or decide what to test.

When to Use

Use this skill when the user asks to:

  • analyze a competitor's active ads
  • search Meta/Facebook, Google, or LinkedIn ad libraries
  • extract ad hooks, CTAs, claims, offers, and landing page angles
  • compare ad messaging across competitors
  • summarize video ad transcripts
  • generate ad test ideas from competitor ads

Data Sources

| Ad library | Search/list endpoint | Detail endpoint | Transcript endpoint |

|---|---|---|---|

| Meta/Facebook | /v1/facebook/adLibrary/search/ads, /v1/facebook/adLibrary/company/ads, /v1/facebook/adLibrary/search/companies | /v1/facebook/adLibrary/ad | /v1/facebook/adLibrary/ad/transcript |

| Google | /v1/google/adLibrary/advertisers/search, /v1/google/company/ads | /v1/google/ad | n/a |

| LinkedIn | /v1/linkedin/ads/search | /v1/linkedin/ad | n/a |

Workflow

  1. Find the advertiser
  • Use company search endpoints when the user provides only a brand name.
  • Use domain/advertiser/page IDs when available.
  1. Fetch active ads
  • Prefer active ads unless the user asks for historical analysis.
  • Capture platform, advertiser/page, ad ID, start date, creative type, text, headline, CTA, destination URL, and source URL.
  1. Fetch details for representative ads
  • Enrich the ads with detail endpoints.
  • For video Meta ads, fetch transcripts when available.
  1. Cluster messaging

Group ads by:

  • pain point
  • persona
  • offer
  • proof/social proof
  • feature/benefit
  • objection handled
  • comparison/alternative angle
  • urgency/discount
  1. Extract swipeable elements
  • hooks
  • headlines
  • primary text patterns
  • CTAs
  • claims
  • offers
  • visual/creative concepts
  1. Recommend tests

Suggest tests based on repeated patterns and gaps, not random ideas.

Output Format

# Ad Library Teardown: {brand}

## Summary
- Ads analyzed: {count}
- Platforms: Meta / Google / LinkedIn
- Main positioning:
- Strongest repeated offer:

## Messaging Angles
| Angle | Evidence | Example ads | Notes |
|---|---|---|---|

## Hooks and Headlines Swipe File
- "..."
- "..."

## Offers and CTAs
| Offer | CTA | Platform | Example |
|---|---|---|---|

## Video Transcript Notes
- [Ad](url): summary, hook, best quote

## What They Appear to Be Testing
1. ...
2. ...

## Recommended Tests for Us
1. ...
2. ...
3. ...

## Sources
- [Ad](url)

Common Pitfalls

  • Do not claim an ad is winning just because it is active. Say it is active or repeated; performance is not public unless the endpoint returns it.
  • Do not ignore repeated ads. Repetition is often a useful signal.
  • Do not invent spend, conversion rate, or targeting unless public data includes it.
  • Do not skip video transcripts when the user asks for hooks or messaging from video ads.

想直接用这个技能?

本站把开放许可(MIT / Apache 等)的技能按仓库打包整理到网盘,点一下转存到你自己的网盘,不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接,不打包。